Nicholas I. Kolkin

Learn More
We present the Word Mover’s Distance (WMD), a novel distance function between text documents. Our work is based on recent results in word embeddings that learn semantically meaningful representations for words from local cooccurrences in sentences. The WMD distance measures the dissimilarity between two text documents as the minimum amount of distance that(More)
We propose an approach for learning category-level semantic segmentation purely from image-level classification tags indicating presence of categories. It exploits localization cues that emerge from training classification-tasked convolutional networks, to drive a “self-supervision” process that automatically labels a sparse, diverse training set of points(More)
Covariance matrices are an effective way to capture global spread across local interest points in images. Often, these image descriptors are more compact, robust and informative than, for example, bags of visual words. However, they are symmetric and positive definite (SPD) and therefore live on a non-Euclidean Riemannian manifold, which gives rise to(More)
In many computer vision tasks, for example saliency prediction or semantic segmentation, the desired output is a foreground map that predicts pixels where some criteria is satisfied. Despite the inherently spatial nature of this task commonly used learning objectives do not incorporate the spatial relationships between misclassified pixels and the(More)
  • 1